Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.8403. Min Act: -0.1700
Data Index: 8147070 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.4965. Min Act: -0.1700
Data Index: 3997341 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.3715. Min Act: -0.1700
Data Index: 2682584 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.3090. Min Act: -0.1700
Data Index: 4830121 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.2778. Min Act: -0.1700
Data Index: 5732368 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.2778. Min Act: -0.1700
Data Index: 4187564 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.2778. Min Act: -0.1700
Data Index: 7362447 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.2153. Min Act: -0.1700
Data Index: 7907981 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.1840. Min Act: -0.1700
Data Index: 2238958 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.1215. Min Act: -0.1700
Data Index: 2098937 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.1215. Min Act: -0.1700
Data Index: 7366146 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.0903. Min Act: -0.1700
Data Index: 3078307 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.0903. Min Act: -0.1700
Data Index: 6963194 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.0903. Min Act: -0.1700
Data Index: 724635 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.1215. Min Act: -0.1700
Data Index: 3985331 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.0903. Min Act: -0.1700
Data Index: 4979193 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.0903. Min Act: -0.1700
Data Index: 8138340 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.0590. Min Act: -0.1700
Data Index: 4042410 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.0590. Min Act: -0.1700
Data Index: 5067462 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8403. Min Range: -6.8403
Max Act: 6.0590. Min Act: -0.1700
Data Index: 4708727 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19